© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 63243
    Prev
    Next
    INDEX
    Explanations

    Unsolvable questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pal
    -0.08
    usal
    -0.08
     langzaam
    -0.07
     tranquilo
    -0.07
     Pal
    -0.07
     khoảng
    -0.07
    ñ
    -0.07
    'aimerais
    -0.07
     tranqu
    -0.07
     धीरे
    -0.07
    POSITIVE LOGITS
     unless
    0.09
     tenzij
    0.09
    unless
    0.09
     невозможно
    0.08
     imme
    0.08
     kidn
    0.08
     տվյալ
    0.08
    restrict
    0.08
     definite
    0.08
     menstrual
    0.08
    Activations Density 0.027%

    No Known Activations